INDEX

Explanations

phrases that express conditions or qualifications related to actions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hips

-0.17

nd

-0.17

IDE

-0.16

_INITIAL

-0.15

idel

-0.15

nds

-0.15

ÑħÑĥ

-0.15

aqu

-0.15

IO

-0.14

ham

-0.14

POSITIVE LOGITS

 Clayton

0.15

 matters

0.14

ering

0.14

agher

0.14

ToObject

0.13

dart

0.13

ithub

0.13

istani

0.13

 Gram

0.13

Activations Density 0.021%

phrases that express conditions or qualifications related to actions

No Comments

No Known Activations